How to convert gpt-neox to llama architecture..?
yuri-son opened this issue · 1 comments
yuri-son commented
Hello developer,
I want to replacing the polyglot based on gpt-neox model with the llama tokenizer and model architecture.
Could you please advise if there's a way to make this conversion?
StellaAthena commented
GPT-NeoX is a library for training models, not a specific architecture. You can find the configs for training a model using the LLaMA architecture in our example configs.